{"id":189058,"url":"https://alion.io/job/krea-ml-researcher-posttraining","title":"ML Researcher - Posttraining","company":{"id":48104,"name":"KREA","domain":"krea.ai","url":"https://alion.io/company/krea","size_band":"1-10","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"B","score":75,"open_postings":3,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-10-24T06:02:35Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["San Francisco, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":171000,"max_usd":377000,"period":"year","method":"role_country_seniority_unknown","sample_n":4194},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":true,"technologies":[{"name":"Diffusion Models","optional":false},{"name":"DPO","optional":false},{"name":"Fine-tuning","optional":false},{"name":"FSDP","optional":false},{"name":"GRPO","optional":false},{"name":"Knowledge Distillation","optional":false},{"name":"LLM","optional":false},{"name":"Model Distillation","optional":false},{"name":"Post-training","optional":false},{"name":"PPO","optional":false},{"name":"PyTorch","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Reward Modeling","optional":false},{"name":"SFT","optional":false},{"name":"SGLang","optional":false},{"name":"vLLM","optional":false},{"name":"VLM","optional":false}],"status":"live","first_seen_at":"2026-09-01T17:38:16Z","employer_posted_date":"2026-09-01","last_verified_at":"2026-10-24T12:56:11Z","board_verified":true,"closed_at":null,"days_open":52,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":52},"description":"About Krea\nAt Krea, we are building next-generation AI creative tools.\nWe're dedicated to making AI intuitive and controllable for creatives - our mission is to build tools that empower human creativity, not replace it. We believe AI is a new medium that allows us to express ourselves through various formats - text, images, video, sound, and even 3D. We're building better, smarter, and more controllable tools to harness this medium. We recently took this a step forward with the launch of Krea 2, our first foundation model, built completely from scratch for aesthetic diversity and stylistic control, and with Krea 3 - our new image editing model.\nWe've raised over $83M and are backed by world-class investors such as a16z, Bain Capital, and Abstract. We work full-time and in-person at our waterfront office in San Francisco. We care about creativity: our team includes musicians, designers, visual artists, and engineers.\nWe're looking for someone with deep experience in large-scale finetuning of diffusion models and posttraining techniques. We have loads of high-quality data and aim to enhance the quality and aesthetics of the models we're building.\nOur culture\nWe work full-time and in-person at our North Beach office in San Francisco.\n\nWe believe that demonstrated interest in the creative space is key: our team includes musicians, designers, visual artists and more.\n\nFast iteration and execution speed. Bias towards action, agency, and independence.\n\nWhat you'll do\nFinetune diffusion models at scale to improve image aesthetics and quality.\n\nImplement posttraining techniques ranging from supervised finetuning, preference optimization, reinforcement learning, on-policy distillation, and various distillation / acceleration techniques.\n\nDesign comprehensive eval suites and reward designs for the reinforcement learning stage focused on image space.\n\nTrain custom VLM as reward models as part of our reward design.\n\nTrain custom LLMs for prompt expansion through finetuning and reinforcement learning.\n\nCoordinate with data teams and partners to manage collection of preference data and model evaluation results.\n\nWork on safety alignment of our models for open source release.\n\nCollaborate with our AI research and engineering teams to integrate advancements into our products.\n\nWhat we're looking for\nProven work of posttraining diffusion models for image or video generation.\n\nExperience with large-scale model training, inference, and optimization.\n\nStrong understanding of both LLM and diffusion post training pipelines and algorithms such as PPO, GRPO, DPO, OPD, and MOPD.\n\nStrong proficiency in PyTorch and understanding of its inner workings.\n\nStrong background in distributed training paradigms such as FSDP, CP, SP, USP, TP, and EP. Knowing how different parallelism strategies work together and their tradeoffs.\n\nGood knowledge of low precision training / inference in FP8, NVFP4, and MXFP8.\n\nGood understanding of algorithms and techniques used in fast inference engines such as vLLM and sglang as well as existing RL frameworks in LLM space such as slime, miles, tinker, and verl.\n\nUnderstanding of various RL infrastructure and optimization techniques such as async RL, fast weight transfer, pipelining rollouts, managing off policy data.\n\nAbility to monitor model regression and identify weak areas and turn them into concrete evals and reward design.\n\nExperience training VLM models. Many of our custom reward models use VLM to provide reward signals for our models.\n\nKeeping up with the developments in related fields such as LLM, VLM, representation learning, and robotics research.\n\nBeing comfortable working in a goal-oriented research environment.\n\nHaving good judgement around when one should explore different training strategies and when it's time to commit to a specific strategy to scale compute and data.\n\nComfortable working with underspecified goals. We expect every technical member to take an ambiguous research goal and break it down into concrete requirements, plans, experiment plan, and execution items.\n\nGood research taste - bias towards simplicity and methods that scale well with compute, data, and minimal human supervision.\n\nWhat we offer\nTeam: Work alongside a world-class team building the future of AI creative tooling\n\nImpact: Significant scope and company-wide impact\n\nCompetitive compensation: generous salary & equity packages\n\nHealth & wellness: 100% health & 99% dental/vision insurance premiums covered for employees, health FSA accounts, & long-term disability coverage\n\nTime off: Flexible PTO policy\n\nFinancial planning: 401k with a 4% company-sponsored match\n\nMeals in the office: breakfast, lunch, dinner - you name it, we'll cover it\n\nTransit: Ubers covered to & from the office\n\nSponsorship: We're open to sponsoring international visas where we can (e.g., STEM OPT, OPT, H-1B, O-1, E-3).\n\nAnd more!\n\nPlease note the above benefits & perks are for full-time employees","description_format":"text","description_chars":4945,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":["401k plan","Equity","Vision insurance"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Generative Image"],"lifecycle":[{"event":"open","at":"2026-09-02T07:49:20Z"}],"visa":[{"country":"US","licensed_sponsor":true,"evidence":"H-1B filings in 12 months: 1","filings_12m":1,"filings_prev_12m":4,"green_card_filings_12m":0,"median_offered_wage_usd":107500,"route":null,"cap_exempt":false,"checked_at":"2026-10-15T11:24:14+00:00","sources":["US Department of Labor: LCA disclosure data (H-1B, H-1B1, E-3)"],"filings_for_role_12m":0}],"liveness":{"score":9,"band":"cold","label":"Long shot","p_open":1,"p_active":0.263,"p_room":0.35,"age_days":52,"expected_fill_days":25,"reasons":["conf:1","win:tail"],"computed_at":"2026-10-24T06:02:35Z"},"pay":null,"html_url":"https://alion.io/job/krea-ml-researcher-posttraining","json_url":"https://alion.io/job/krea-ml-researcher-posttraining.json","meta":{"generated_at":"2026-10-24T13:16:11Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":18295,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-25T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":48104},"rest":"https://alion.io/mcp/rest/get_company?id=48104"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fkrea-ml-researcher-posttraining"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fkrea-ml-researcher-posttraining"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fkrea-ml-researcher-posttraining"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/krea-ml-researcher-posttraining\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fkrea-ml-researcher-posttraining"}]}